© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 92534
    Prev
    Next
    INDEX
    Explanations

    grief and bereavement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aspirations
    -0.85
     conformément
    -0.84
    IntoConstraints
    -0.83
     Relax
    -0.82
    热血
    -0.82
    紧张
    -0.80
    \|_{\
    -0.79
     więcej
    -0.77
     Dest
    -0.77
     redemption
    -0.77
    POSITIVE LOGITS
     grief
    3.17
     grieving
    2.89
     grieve
    2.38
     mourning
    2.38
     Grief
    2.36
    Grief
    2.33
     bereavement
    2.08
     mourners
    2.06
     Grie
    1.92
     bereaved
    1.92
    Activations Density 0.044%

    No Known Activations